Abstract
This paper is a systematic study of artificial neural network applications for the diagnosis of power transformer incipient fault. Diagonal recurrent neural network (DRNN) is used to realize the intelligent fault diagnosis for oil-filled power transformer based on dissolved gas-in-oil analysis(DGA). In order to obtain better detection results and improve the accuracy of detection, the photoacoustic spectroscopy (PAS) technique is applied to the transformer on-line monitoring system. To overcome disadvantages of BP algorithm, a new recursive prediction error (RPE) algorithm is proposed and implemented in this paper. In addition, to demonstrate the effectiveness and veracity of the proposed on-line monitoring system, a large number of experimental studies have been carried out, and the experimental results are satisfactory.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call